Learning approach to optical tomography

Abstract

Optical tomography has been widely investigated for biomedical imaging applications. In recent years optical tomography has been combined with digital holography and has been employed to produce high-quality images of phase objects such as cells. In this paper we describe a method for imaging 3D phase objects in a tomographic configuration implemented by training an artificial neural network to reproduce the complex amplitude of the experimentally measured scattered light. The network is designed such that the voxel values of the refractive index of the 3D object are the variables that are adapted during the training process. We demonstrate the method experimentally by forming images of the 3D refractive index distribution of Hela cells.

GPU-based deep convolutional neural network for tomographic phase microscopy with ℓ1 fitting and regularization

“…To deal with the vast quantities of parameters and regularizers, we apply the adaptive moment estimation (Adam) algorithm 26 for optimization, which can also be regarded as the training process of the CNN. Compared with previous works using stochastic gradient descent, 23,24 our method ensures a faster convergence and a better robustness to the initial value. Both simulation and experimental results on polystyrene beads, and HeLa cells are shown to validate its reconstruction performance.…”

“…21,22 And the multislice propagation modeling is definitely similar to the neural network in the field of machine learning. 23,24 By combining the nonlinear modeling and the sparse constraint in the gradient domain, the Psaltis group has validated the competitive capability of this learning approach over conventional methods. 21,23 Despite its success in modeling with l 2 -norm constraint, the current method is still a preliminary network, especially compared with the state-of-the-art deep learning frameworks, 25 and the iterative reconstruction is challenging to deploy in practice due to the high computational cost and the difficulty of the hyperparameter selection.…”

“…Figure 1 shows the schematic diagram of the experimental setup. In our system, 23 the sample placed between two cover glasses is illuminated sequentially at multiple angles and the scattered light is holographically recorded. A laser beam (λ ¼ 561 nm) is split into sample and reference arms by the first beam splitter.…”

GlobalBioIm: A Unifying Computational Framework for Solving Inverse Problems

“…These measurements can take the form of traditional images, as in the case of 3D deconvolution microscopy [1], interferograms/holograms, modulations [2], or 2D projections of a specimen as in refractive-index tomography [3].…”

Learning from Examples in Optical Imaging

“…However, in order to surpass the current limits in term of resolution and penetration, multiple scattering has to be taken into account. A recently investigated approach is to build a digital model of the object, represented by its refractive index distribution, and to optimize it so that it matches the experimental measurements [4][5][6]. The physical forward model that relates the refractive index to the measured scatted field can be chosen so that it includes multiple scattering.…”